Triple
T3282529
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arthur Dimmesdale |
E68904
|
entity |
| Predicate | secret |
P22701
|
FINISHED |
| Object | adultery with Hester Prynne |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: adultery with Hester Prynne | Statement: [Arthur Dimmesdale, secret, adultery with Hester Prynne]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secret Context triple: [Arthur Dimmesdale, secret, adultery with Hester Prynne]
-
A.
secretive
Indicates that an entity deliberately withholds information or conceals its thoughts, actions, or intentions from others.
-
B.
keepsSecretAbout
chosen
Indicates that one entity intentionally withholds or conceals information regarding another specified entity or topic from others.
-
C.
revealedSecretOf
Indicates that one entity has disclosed or exposed confidential or previously unknown information belonging to another entity.
-
D.
negotiatedInSecret
Indicates that the parties conducted negotiations privately, without public knowledge or disclosure.
-
E.
secretProtocolContent
Indicates that one entity contains or represents the confidential or undisclosed details of a protocol associated with another entity.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ad859c463481909ca4be267336c290 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb0345d448190a1f936abe7748e33 |
completed | March 8, 2026, 5:21 p.m. |
| PD | Predicate disambiguation | batch_69ada421fadc8190b7c7d3c8afd20061 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:10 p.m.